Hot Spot Police Patrolling with Predictive Models vs.Crime Analysts
Axios
Policing
Solution types
Hot Spots Policing
Problems addressed
Crime and delinquency (multiple types)
Effectiveness

Effective

.

.

.

.

.

Effective

Want to know more about this classification? Check out our methodological manual.

Life periods served
People of all ages
Where the program was applied
Community (streets or community centers)
Country of application
United States
Description

This study compares hot spot patrols that use predictive policing models with patrols that use crime analysts.
In patrols based on a predictive policing model, officers were encouraged to choose the most appropriate techniques to intervene in the predicted areas. Officers in patrols based on the predictions of trained crime analysts applied short-term interventions to small areas indicated based on their emerging problems.
The intervention lasted five to eight months on both police fronts.

Impact evaluations

An impact assessment showed a reduction of 4.3 fewer crimes per week at average patrol levels, or an average 7.4% reduction in crime volume as a function of patrol time. The authors suggest that a dynamic police patrol in response to crime forecasts (Epidemic-Type Aftershock Sequence, ETAS) can interrupt crime opportunities and lead to real reductions in crime [1].

Bibliographic reference

[1] Mohler, G. O., Short, M. B., Malinowski, S., Johnson, M., Tita, G. E., Bertozzi, A. L. & Brantingham, P. J. (2015). Randomized Controlled Field Trials of Predictive Policing. Journal of the American Statistical Association, 110(512), 1399–1411. https://doi.org/10.1080/01621459.2015.1077710

Information source